RecallNest

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It successfully discloses the read-only nature and aggregation behavior (combining multiple sources), but lacks critical behavioral details such as return format, error handling when sessionId is invalid, or behavior when no checkpoint exists.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight statements totaling one sentence plus fragments: the action (compose), the safety property (read-only), and the usage trigger (when entering). Every word earns its place; no redundancy or boilerplate.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 7 optional parameters and no output schema, the description adequately explains the conceptual output (aggregated context) but omits the structure or format of what is returned. For a tool of this complexity without annotations, it meets minimum viability but leaves gaps in behavioral contract documentation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, establishing a baseline of 3. The description mentions conceptual mappings (e.g., 'latest checkpoint' relates to includeLatestCheckpoint/sessionId) but adds no usage guidance, syntax details, or examples beyond what the schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool composes 'startup context' by combining specific sources (durable memory, patterns, cases, checkpoint). The 'Read-only' declaration distinguishes it from sibling write-tools like store_memory or checkpoint_session, though it doesn't explicitly contrast with search_memory or latest_checkpoint.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit temporal guidance: 'Use when entering a new session and you need to recover prior decisions, open loops, and next actions.' This clearly signals the session-initiation use case. However, it does not explicitly name alternatives (e.g., 'use search_memory instead for targeted queries').

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.